Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numeric values and measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     secondly
    -0.89
     afterwards
    -0.74
     Secondly
    -0.71
    ipal
    -0.70
     thereafter
    -0.70
    taker
    -0.63
     barracks
    -0.63
     altar
    -0.61
     reverted
    -0.61
    Secondly
    -0.60
    POSITIVE LOGITS
     TODAY
    0.91
     researchers
    0.83
     infographic
    0.82
     Mehran
    0.81
    Researchers
    0.80
     NPR
    0.79
    NPR
    0.75
     Mayo
    0.75
    Fortunately
    0.71
    Solution
    0.71
    Act Density 0.976%

    No Known Activations